Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 768 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0002

Data Index: 934728 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0280. Min Act: -0.0001

Data Index: 361628 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0278. Min Act: -0.0001

Data Index: 303590 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1216845 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0269. Min Act: -0.0002

Data Index: 677414 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0272. Min Act: -0.0001

Data Index: 247092 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0278. Min Act: -0.0002

Data Index: 976148 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0266. Min Act: -0.0002

Data Index: 721043 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0277. Min Act: -0.0001

Data Index: 917659 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1245416 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0256. Min Act: -0.0001

Data Index: 527743 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0275. Min Act: -0.0001

Data Index: 643956 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0269. Min Act: -0.0001

Data Index: 567305 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0230. Min Act: -0.0002

Data Index: 450701 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1309530 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1019125 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0249. Min Act: -0.0001

Data Index: 589021 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0244. Min Act: -0.0001

Data Index: 827076 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0255. Min Act: -0.0001

Data Index: 590486 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1411251 (Python Code)

Max Activating Token Index: 939